ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified productivity Safety 4/5

granola

Access Granola AI meeting notes via MCP (mcporter). Query meetings, list by date range, get full details, and pull verbatim transcripts. Use when the user asks about meeting notes, what was discussed, action items, decisions, or anything from their meetings. Also handles OAuth token refresh when calls fail with auth errors.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/bholagabbar/granola-mcp
Or

What This Skill Does

The Granola MCP skill for OpenClaw integrates your Granola AI meeting notes directly into your AI agent workflow. By leveraging the mcporter framework, it allows the agent to intelligently query, list, and retrieve detailed meeting insights, action items, and verbatim transcripts. This skill acts as a bridge between your Granola account and the agent, enabling you to treat your meeting notes as a searchable knowledge base. It handles authentication gracefully, including automated token refreshing, ensuring that your agent always has persistent access to your meeting history.

Installation

To install this skill, run the following command in your terminal within your OpenClaw environment: clawhub install openclaw/skills/skills/bholagabbar/granola-mcp

After installation, follow these configuration steps:

  1. Complete the OAuth handshake at https://mcp-auth.granola.ai/oauth2/authorize.
  2. Store your credentials in config/granola_oauth.json.
  3. Configure your config/mcporter.json with the necessary authorization headers.
  4. Ensure you set up the token refresh script (scripts/refresh_token.sh) to prevent downtime caused by token expiration.

Use Cases

This skill is perfect for professionals who juggle multiple meetings and need to recall specific information without scrubbing through recordings. Use it for:

  • Summarizing key decisions from a high-stakes project meeting.
  • Extracting action items assigned to you or your team members.
  • Searching for specific quotes or verbatim statements from client calls.
  • Comparing meeting topics across different dates.
  • Preparing for follow-up meetings by reviewing what was discussed in previous sessions.

Example Prompts

  • "What were the final design decisions we reached in the Tuesday product sync?"
  • "List all meetings I had regarding the Q4 budget last week and give me a summary of each."
  • "Find the exact quote from Sarah about the API limitations during the integration call yesterday."

Tips & Limitations

  • Natural Language First: Always prefer query_granola_meetings for most requests; it is optimized for context and semantic understanding.
  • Authentication Errors: If the agent returns a 401 error, it indicates the token has expired. Manually execute the refresh_token.sh script to restore connectivity.
  • Rate Limits: When retrieving transcripts, be mindful that excessive calls in short windows may hit API limits. The agent will handle these gracefully, but batching is recommended for high-volume tasks.
  • Security: Ensure that the config/ directory is added to your .gitignore file, as it contains sensitive OAuth secrets that must not be exposed to version control systems.

Metadata

Stars4473
Views1
Updated2026-05-01
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-bholagabbar-granola-mcp": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#granola#meetings#productivity#transcripts#mcp
Safety Score: 4/5

Flags: network-access, file-read, file-write, external-api